Learn how algorithms and data science reshape portfolio management. This eight-month intensive program runs from September 2025 to April 2026, covering everything from fundamental concepts to real-world model deployment in Bangkok's financial sector.
We structure the program around projects you'll complete, not abstract theory. Each module introduces concepts through problems that investment teams actually face. You'll work with real market data from Thai and regional exchanges, building tools that could slot into an active portfolio management workflow.
Before jumping into neural networks, you need solid grounding in probability and statistics. We start with time series analysis of SET index components, teaching you to spot patterns that matter and ignore noise that doesn't. By week six, you'll have built your first prediction model using regression techniques.
Here's where things get practical. You'll train models to predict short-term price movements using various algorithms. We cover decision trees, random forests, and gradient boosting. The focus stays on understanding why a model makes certain predictions, not just achieving high accuracy scores on test data.
Neural networks can extract signals from sources traditional analysis misses. We work with sentiment data from financial news, social media activity, and satellite imagery. You'll build LSTM networks for sequence prediction and experiment with transformer architectures adapted for financial time series.
Machine learning creates opportunities but also new risks. This module teaches you to quantify model uncertainty, design position sizing algorithms, and build portfolios that balance predicted returns against potential losses. We stress-test strategies against historical market crashes and regime changes.
A model that works in Jupyter notebooks isn't finished. The final weeks focus on deployment: building APIs, handling live data feeds, monitoring model performance, and detecting when strategies stop working. You'll implement a complete trading system that runs autonomously and alerts you when intervention becomes necessary.
Meet Your Instructors
Our teaching team includes quantitative analysts who've deployed models at scale. They understand the gap between academic research and production systems because they've navigated it themselves.
Lead Quantitative Strategist
Spent twelve years building algorithmic trading systems for European and Asian markets. Kasper focuses on teaching students to recognize when simple models outperform complex ones.
Machine Learning Engineer
Built production ML systems for fintech startups across Southeast Asia. Brennan teaches the engineering practices that keep models running reliably after deployment, including proper monitoring and graceful degradation.
Data Science Specialist
Worked on alternative data integration at hedge funds in Singapore and Bangkok. Tavish covers feature engineering techniques and helps students identify which data sources actually contain predictive signals versus expensive noise.
